---
title: "HR Movement dashboard"
output: 
  flexdashboard::flex_dashboard:
    orientation: rows
    vertical_layout: fill
    source_code: embed
---


```{r setup, include=FALSE}
# Dashboard
library(flexdashboard)
# Data manipulation
library(tidyverse)      # data manipulation & plotting
library(stringr)        # text cleaning and regular expressions
library(tidytext)       # provides additional text mining functions
library(textdata)
library(dplyr)
# Plots
library(viridis)
library(wordcloud2)
#devtools::install_github("gaospecial/wordcloud2")
#library("gaospecial/wordcloud2")
library(RColorBrewer)
library(tm)
library(ggplot2)
library(emojifont)
library(plotly)
library(gridExtra)
# PieChart
library(lessR)
# Network
library(igraph)
library(ggraph)
library(ggiraph)
#devtools::install_github("dgrtwo/drlib")


```


```{r}
data <- read.csv("facebook_dataset.csv", header=TRUE, stringsAsFactors = FALSE)
data$page_name<-""
data[data$page_id=="86680728811",]$page_name<-"abc"
data[data$page_id=="228735667216",]$page_name<-"bbc"
data[data$page_id=="5550296508",]$page_name<-"cnn"
data[data$page_id=="15704546335",]$page_name<-"fox"
data[data$page_id=="5863113009",]$page_name<-"laTimes"
```


Dataset {data-icon="fa-table"}
=============================

### Descripción del dataset

El conjunto de datos ha sido tomado de [data.world] (https://data.world/martinchek/2012-2016-facebook-posts) y pertenecen a un [artículo] (https://shift.newco.co/2016/11/09/What-I-Discovered-About-Trump-and-Clinton-From-Analyzing-4-Million-Facebook-Posts/) que analizó 4 millones de publicaciones de Facebook para observar que información había sobre Donald Trump y Hilary Clinton. 

Por ello, el conjunto contiene publicaciones de Facebook escritos entre 2012 y 2016 por 15 de los principales medios de comunicación.

Los datos se encuentran agrupados (en csv) por medio de comunicación, por lo que para este caso solo he escogido 5 de esos medios para reducir los costes que puede tener analizar un conjunto de datos tan grande.


Por tanto, el dataset generado se trata de un conjunto de 154.173 filas, cada una de las cuales corresponde a una **publicación de Facebook** realizada por algunas de las siguientes páginas:

- **BBC** (id 228735667216): The British Broadcasting Corporation.

- **CNN** (id 5550296508): Multinational cable news channel headquartered in Atlanta, Georgia, 
U.S.

- **Fox** (id 15704546335): The Fox News Channel.

- **ABC** (id 86680728811): ABC News is the news division of the American broadcast network ABC.

- **LA Times** (id 5863113009): Los Angeles Times: News from California, the nation and world.

### Previsualización de los datos

```{r}
head(data)
```
### Resumen de los campos

```{r}
summary(data)

```


General {data-icon="fa-chart-line"}
=============================

Row {data-width=150}
--------------------------------------
### Número de Publicaciones
```{r}
total_post <- nrow(data)

valueBox(value = total_post,icon = "fa-facebook",caption = "Número de Publicaciones",color = "#C1FFC1")
```

### Número de páginas
```{r}
total_pages <- length(unique(data$page_id))

valueBox(value = total_pages,icon = "fa-file",caption = "Número de páginas", color = "#FFD700")
```

### Número de likes
```{r}
likes_total <- sum(data$likes_count)

valueBox(value = likes_total,icon = "fa-thumbs-up",caption = "Número de likes", color = "#FFEC8B")
```


Row {data-width=150}
--------------------------------------
### Número de enlaces

```{r}
link_post <- length(data[data$post_type == "link",])

valueBox(value = link_post,icon = "fa-link",caption = "Número de enlaces",color = "#EEEEE0")
```

### Número de vídeos
```{r}
video_post <- length(data[data$post_type == "video",])

valueBox(value = video_post,icon = "fa-video",caption = "Número de vídeos", color = "#BF3EFF")
```

### Número de canciones
```{r}
music_post <- length(data[data$post_type == "music",])

valueBox(value = music_post,icon = "fa-music",caption = "Número de canciones", color = "#7FFFD4")
```


Row {data-width=150}
--------------------------------------
### Número de eventos

```{r}
event_post <- length(data[data$post_type == "event",])

valueBox(value = event_post,icon = "fa-calendar",caption = "Número de eventos",color = "#FFA07A")
```


### Número de fotos
```{r}
photo_post <- length(data[data$post_type == "photo",])

valueBox(value = 22,icon = "fa-image",caption = "Número de fotos", color = "#FF3030")
```

### Número de comentarios
```{r}
comments_total <- sum(data$comments_count)

valueBox(value = music_post,icon = "fa-comment",caption = "Número de comentarios", color = "#E0FFFF")
```



Row {data-height=500}
----------------------------------

<div style="height:500px">

### Número de publicaciones según el tipo

```{r}
data_post_type <- data %>% dplyr::group_by(post_type)

plot <- ggplot(data = data_post_type, aes(x = post_type, fill=post_type)) +
  geom_bar() +
  labs(x = "Tipo de publicación", y = "Nº publicaciones")
ggplotly(plot)
```

</div>


### Número de publicaciones por página y tipo

```{r}
data_by_page_type <- data %>% dplyr::group_by(page_name, post_type) %>%
  dplyr::summarise(total = n()) 

# Small multiple
plot <- ggplot(data_by_page_type, aes(fill=post_type, y=total, x=page_name)) + 
    geom_bar(position="stack", stat="identity") +
    scale_fill_viridis(discrete = T) +
    xlab("Página") +
  ylab("Nº publicaciones")
ggplotly(plot)
```


Row 
----------------------------------

<div style="height:500px">
### Agrupación por año 

```{r}
data_month <- data %>% dplyr::group_by(lubridate::month(date),lubridate::year(date)) %>%
  dplyr::summarise(total = n()) %>% dplyr::arrange(desc(total))
colnames(data_month) <- c("month", "year", "total")

data_month$month <- as.character(data_month$month)
data_month$year <- as.character(data_month$year)
data_month$month <- factor(data_month$month, levels = c("1","2","3","4","5","6", "7","8","9", "10", "11", "12"), labels = c("01","02","03","04","05","06", "07","08","09", "10", "11", "12"))
data_month <- data_month[order(data_month$month),]


plot <- ggplot(data=data_month, mapping=aes(x=month, y=total, shape=year, color=year)) +
  geom_point() +
  geom_line(aes(group = 1)) + 
  facet_grid(facets = year ~ ., margins = FALSE) + theme_bw() + 
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1), plot.title = element_text(hjust = 0.5)) +
  ggtitle("Número de publicaciones por mes y año") +
  xlab("Mes") +
  ylab("Nº publicaciones")

ggplotly(plot)
```

</div>

<div style="height:500px">
### Visión global

```{r}
plot <- ggplot(data=data_month, mapping=aes(x=month, y=total, shape=year, color=year)) +
  geom_point() +
  geom_line(aes(group = 1))+ 
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1), plot.title = element_text(hjust = 0.5))+  
  ggtitle("Número de publicaciones por mes y año") + 
  xlab("Mes") + 
  ylab("Nº publicaciones")

ggplotly(plot)
```
</div>

Row 
----------------------------------

<div style="height:600px">

### Número de publicaciones por página y año 

```{r}
data_by_page <- data %>% dplyr::group_by(page_name, lubridate::year(date)) %>%
  dplyr::summarise(total = n()) %>% dplyr::arrange(desc(total))

colnames(data_by_page) <- c("page", "year", "total")
data_by_page <- data_by_page[!is.na(data_by_page$page),]
data_by_page$page <- as.character(data_by_page$page)

plot <- ggplot(data_by_page, aes(year, page)) + 
  geom_point(aes(size=total), colour = "red") +
  scale_color_manual(values=c("black", "dodgerblue")) +
  ggtitle("Publicaciones por página y año") +
  theme(legend.position = 'none', plot.title = element_text(hjust = 0.5)) +
  xlab("Año") + 
  ylab("Página")

ggplotly(plot)
```

</div>


Reacciones {data-icon="fa-comments"}
===

Row 
-----------------------------------------------------------------------


```{r}
emojis <- c(#emoji("email"),# share
  #emoji("thumbsup"),# like
  emoji("heart"),# love
  emoji("joy"),# haha
  emoji("cry"),# sad
  emoji("rage"),# angry
  emoji("innocent")# thankfull
  )

#names <- c("shares","likes","love","haha","sad","angry", "thankfull")
names <- c("love","haha","sad","angry", "thankfull")

```



<div style="height:400px">

### Reacciones BBC

```{r}
data_bbc <- tibble(names = names,
       emoji = emojis,
       total = c(#sum(data$shares_count[data$page_name=="bbc"]),
                 #sum(data$likes_count[data$page_name=="bbc"]),
                 sum(data$love_count[data$page_name=="bbc"]),
                 sum(data$haha_count[data$page_name=="bbc"]),
                 sum(data$sad_count[data$page_name=="bbc"]),
                 sum(data$angry_count[data$page_name=="bbc"]),
                 sum(data$thankful_count[data$page_name=="bbc"])
                 ))

plot <- ggplot(data_bbc, aes(names, total, label = emoji, fill=names)) + 
  geom_bar(stat = "identity") +
  geom_text(family = "EmojiOne", size = 6, vjust = -.5) +
  scale_x_discrete(breaks = data_bbc$names, labels = data_bbc$emoji) +
  ggtitle("Reacciones a las publicaciones de BBC") +
  theme(axis.title.x=element_blank(),
        axis.text.x=element_blank(),
    axis.ticks.x=element_blank()) +
  xlab("Reacción")

ggplotly(plot)
```

</div>

### Reacciones CNN

```{r}
data_cnn <- tibble(names = names,
       emoji = emojis,
       total = c(#sum(data$shares_count[data$page_name=="cnn"]),
                 #sum(data$likes_count[data$page_name=="cnn"]),
                 sum(data$love_count[data$page_name=="cnn"]),
                 sum(data$haha_count[data$page_name=="cnn"]),
                 sum(data$sad_count[data$page_name=="cnn"]),
                 sum(data$angry_count[data$page_name=="cnn"]),
                 sum(data$thankful_count[data$page_name=="cnn"])
                 ))

plot <- ggplot(data_cnn, aes(names, total, label = emoji, fill=names)) + 
  geom_bar(stat = "identity") +
  geom_text(family = "EmojiOne", size = 6, vjust = -.5) +
  scale_x_discrete(breaks = data_cnn$names, labels = data_cnn$emoji) +
  ggtitle("Reacciones a las publicaciones de CNN") +
  theme(axis.title.x=element_blank(),
        axis.text.x=element_blank(),
    axis.ticks.x=element_blank()) +
  xlab("Reacción")

ggplotly(plot)

```


### Reacciones ABC

```{r}
data_abc <- tibble(names = names,
       emoji = emojis,
       total = c(#sum(data$shares_count[data$page_name=="bbc"]),
                 #sum(data$likes_count[data$page_name=="bbc"]),
                 sum(data$love_count[data$page_name=="abc"]),
                 sum(data$haha_count[data$page_name=="abc"]),
                 sum(data$sad_count[data$page_name=="abc"]),
                 sum(data$angry_count[data$page_name=="abc"]),
                 sum(data$thankful_count[data$page_name=="abc"])
                 ))

plot <- ggplot(data_abc, aes(names, total, label = emoji, fill=names)) + 
  geom_bar(stat = "identity") +
  geom_text(family = "EmojiOne", size = 6, vjust = -.5) +
  scale_x_discrete(breaks = data_abc$names, labels = data_abc$emoji) +
  ggtitle("Reacciones a las publicaciones de ABC") +
  theme(axis.title.x=element_blank(),
        axis.text.x=element_blank(),
    axis.ticks.x=element_blank()) +
  xlab("Reacción")

ggplotly(plot)
```

Row 
-----------------------------------------------------------------------

<div style="height:400px">


### Reacciones The Fox

```{r}
data_fox <- tibble(names = names,
       emoji = emojis,
       total = c(#sum(data$shares_count[data$page_name=="fox"]),
                 #sum(data$likes_count[data$page_name=="fox"]),
                 sum(data$love_count[data$page_name=="fox"]),
                 sum(data$haha_count[data$page_name=="fox"]),
                 sum(data$sad_count[data$page_name=="fox"]),
                 sum(data$angry_count[data$page_name=="fox"]),
                 sum(data$thankful_count[data$page_name=="fox"])
                 ))

plot <- ggplot(data_fox, aes(names, total, label = emoji, fill=names)) + 
  geom_bar(stat = "identity") +
  geom_text(family = "EmojiOne", size = 6, vjust = -.5) +
  scale_x_discrete(breaks = data_fox$names, labels = data_fox$emoji) +
  ggtitle("Reacciones a las publicaciones de The Fox News Channel") +
  theme(axis.title.x=element_blank(),
        axis.text.x=element_blank(),
    axis.ticks.x=element_blank()) +
  xlab("Reacción")

ggplotly(plot)
```

</div>

### Reacciones LA Times

```{r}
data_laTimes <- tibble(names = names,
       emoji = emojis,
       total = c(#sum(data$shares_count[data$page_name=="laTimes"]),
                 #sum(data$likes_count[data$page_name=="laTimes"]),
                 sum(data$love_count[data$page_name=="laTimes"]),
                 sum(data$haha_count[data$page_name=="laTimes"]),
                 sum(data$sad_count[data$page_name=="laTimes"]),
                 sum(data$angry_count[data$page_name=="laTimes"]),
                 sum(data$thankful_count[data$page_name=="laTimes"])
                 ))

plot <- ggplot(data_laTimes, aes(names, total, label = emoji, fill=names)) + 
  geom_bar(stat = "identity") +
  geom_text(family = "EmojiOne", size = 6, vjust = -.5) +
  scale_x_discrete(breaks = data_laTimes$names, labels = data_laTimes$emoji) +
  ggtitle("Reacciones a las publicaciones de Los Angeles Times") +
  theme(axis.title.x=element_blank(),
        axis.text.x=element_blank(),
    axis.ticks.x=element_blank()) +
  xlab("Reacción")

ggplotly(plot)
```


Row 
-----------------------------------------------------------------------

<div style="height:400px">


### Donut chart: Reacciones BBC

```{r, message=FALSE, warning=FALSE,  results='hide'}

lessR::PieChart(x=names, 
                y =total, 
                data = data_bbc,
                fill = "viridis", 
                hole = 0.5, 
                main = "BBC",
                values_size=2,
                labels_cex=2,
                main_cex=2)
```

</div>


### Donut chart: Reacciones CNN

```{r, message=FALSE, warning=FALSE,  results='hide'}

lessR::PieChart(x=names, 
                y =total, 
                data = data_cnn,
                fill = "viridis", 
                hole = 0.5, 
                main = "CNN",
                values_size=2,
                labels_cex=2,
                main_cex=2)
```

### Donut chart: Reacciones BBC

```{r, message=FALSE, warning=FALSE,  results='hide'}

lessR::PieChart(x=names, 
                y =total, 
                data = data_bbc,
                fill = "viridis", 
                hole = 0.5, 
                main = "BBC",
                values_size=2,
                labels_cex=2,
                main_cex=2)
```


Row 
-----------------------------------------------------------------------

<div style="height:400px">

### Donut chart: Reacciones The Fox


```{r, message=FALSE, warning=FALSE,  results='hide'}

lessR::PieChart(x=names, 
                y =total, 
                data = data_fox,
                fill = "viridis", 
                hole = 0.5, 
                main = "The Fox",
                values_size=2,
                labels_cex=2,
                main_cex=2)
```

</div>

### Donut chart: Reacciones LA Times


```{r, message=FALSE, warning=FALSE,  results='hide'}

lessR::PieChart(x=names, 
                y =total, 
                data = data_laTimes,
                fill = "viridis", 
                hole = 0.5, 
                main = "LA Times",
                values_size=2,
                labels_cex=2,
                main_cex=2)

```


Análisis de textos y sentimientos {data-icon="fa-user"}
===

Row {.tabset .tabset-fade}
--------


```{r}
get_bigram_filtered <- function(filter_word){
  
  filtered_data <- data %>% dplyr::filter(stringr::str_detect(tolower(message), filter_word))
  filtered_data <- filtered_data[filtered_data$post_type!="link" &    filtered_data$post_type!="photo" ,]
  filtered_data <- filtered_data[, c('page_name', 'name', 'message')]
  
  data_bigram <- filtered_data %>% unnest_tokens(bigram, message, token = "ngrams", n = 2)
  
  data_bigram <- data_bigram %>%
    separate(bigram, c("word1", "word2"), sep = " ") %>%
    filter(!word1 %in% stop_words$word,
           !word2 %in% stop_words$word) %>%
    count(page_name, word1, word2, sort = TRUE) %>%
    unite("bigram", c(word1, word2), sep = " ") %>%
    dplyr::filter(!stringr::str_detect(tolower(bigram), "http")) %>%
    dplyr::filter(!stringr::str_detect(tolower(bigram), "bbc")) %>%
    dplyr::filter(!stringr::str_detect(tolower(bigram), "fox"))

  data_bigram <- by(data_bigram, data_bigram["page_name"], head, n=8)
  data_bigram <- Reduce(rbind, data_bigram)
  data_bigram
}
```

<div style="height:600px">

### Basketball

```{r}
data_bigram_sport <- get_bigram_filtered("basketball")
```


#### Filtered word: Basketball

```{r}
plot1 <- data_bigram_sport %>% 
  mutate(page_name = factor(page_name) %>% forcats::fct_rev()) %>%
  ggplot(aes(drlib::reorder_within(bigram, n, page_name), n, fill = page_name)) +
  geom_bar(stat = "identity", alpha = .8, show.legend = FALSE) +
  drlib::scale_x_reordered() +
  facet_wrap(~ page_name, ncol = 2, scales = "free") +
  coord_flip() +
  ylab("") +
  xlab("") +
  ggtitle("Pares de palabras con mayor ocurrencia por página filtrando por: Basketbal") +
  theme(legend.position = 'none', plot.title = element_text(hjust = 0.5))


ggplotly(plot1) 
```

</div>


<div style="height:600px">

### Image

```{r}
data_bigram_image <- get_bigram_filtered("image")
```

#### Filtered word: Image


```{r}
plot1 <- data_bigram_image %>% 
  mutate(page_name = factor(page_name) %>% forcats::fct_rev()) %>%
  ggplot(aes(drlib::reorder_within(bigram, n, page_name), n, fill = page_name)) +
  geom_bar(stat = "identity", alpha = .8, show.legend = FALSE) +
  drlib::scale_x_reordered() +
  facet_wrap(~ page_name, ncol = 2, scales = "free") +
  coord_flip() +
  ylab("") +
  xlab("") +
  ggtitle("Pares de palabras con mayor ocurrencia por página filtrando por: Image") +
  theme(legend.position = 'none', plot.title = element_text(hjust = 0.5))
  

ggplotly(plot1) 
```

</div>


Row {.tabset .tabset-fade}
--------

```{r}
get_wordcloud_data <- function(filter_word){
  
  filtered_data <- data %>% dplyr::filter(stringr::str_detect(message, filter_word))
  text <- filtered_data$message
  docs <- tm::Corpus(VectorSource(text))
  
  docs <- docs %>%
    tm::tm_map(tm::removeNumbers) %>%
    tm::tm_map(tm::removePunctuation) %>%
    tm::tm_map(tm::stripWhitespace)
  docs <- tm::tm_map(docs, tm::content_transformer(tolower))
  docs <- tm::tm_map(docs, tm::removeWords, tm::stopwords("english"))
  
  dtm <- tm::TermDocumentMatrix(docs) 
  matrix <- as.matrix(dtm) 
  words <- sort(rowSums(matrix),decreasing=TRUE) 
  df <- data.frame(word = names(words),freq=words)
  df <- df %>% mutate_at(vars(word), function(x){gsub('[^ -~]', '', x)})
  df <- df[1:500, ]
}
```

```{r}
data_wordcloud <- get_wordcloud_data("sport")
```

<div style="height:600px">

### Normal


#### Wordcloud normal


```{r message=FALSE}
wordcloud2(data=data_wordcloud, size=1.6, color='random-dark')
```

</div>


<div style="height:600px">

### Color


#### Wordcloud cambiando el color


```{r message=FALSE}
wordcloud2(data=data_wordcloud, size=1.6, color='random-light', backgroundColor="black")
```

</div >

<div style="height:600px; display: flex; justify-content: center;">

### Forma


#### Wordcloud cambiando la forma


```{r message=FALSE}
wordcloud2(data_wordcloud, size = 0.7, shape = 'star')
```

</div>

Row
------

<div style="height:600px">

### Análisis de sentimientos (AFINN)

```{r}
data_bigram_all <- data[, c('page_name', 'name', 'message')]
data_bigram_all <- data_bigram_all %>% unnest_tokens(bigram, message, token = "ngrams", n = 2)

AFINN <- get_sentiments("afinn")

nots <- data_bigram_all %>%
        separate(bigram, c("word1", "word2"), sep = " ") %>%
        filter(word1 == "not")  %>%
        inner_join(AFINN, by = c(word2 = "word")) %>% 
        count(word2, value, sort = TRUE) 

plot <- nots %>%
        mutate(contribution = n * value) %>%
        arrange(desc(abs(contribution))) %>%
        head(20) %>%
        ggplot(aes(reorder(word2, contribution), n * value, fill = n * value > 0)) +
        geom_bar(stat = "identity", show.legend = FALSE) +
        xlab("Palabras precedidas por 'not'") +
        ylab("Sentimiento según el número de ocurrencia") +
        coord_flip() +
        theme(legend.position = 'none')
ggplotly(plot)

```

</div>

Row
-----

<div style="height:800px">

### Red de correlaciones para el filtro Basketball


```{r}

filtered_data <- data %>% dplyr::filter(stringr::str_detect(tolower(message), "trump"))
filtered_data <- filtered_data[, c('page_name', 'name', 'message')]

data_bigram <- filtered_data %>% unnest_tokens(bigram, message, token = "ngrams", n = 2)
data_bigram <- data_bigram %>%
  dplyr::filter(!stringr::str_detect(tolower(bigram), "http")) %>%
  dplyr::filter(!stringr::str_detect(tolower(bigram), "bbc")) %>%
  dplyr::filter(!stringr::str_detect(tolower(bigram), "fox"))

bigram_graph <- data_bigram %>%
        separate(bigram, c("word1", "word2"), sep = " ") %>%
        filter(!word1 %in% stop_words$word,
               !word2 %in% stop_words$word) %>%
        count(word1, word2, sort = TRUE) %>%
        unite("bigram", c(word1, word2), sep = " ") %>%
        filter(n > 50) %>%
        graph_from_data_frame()
```

```{r}
set.seed(123)

a <- grid::arrow(type = "closed", length = unit(.15, "inches"))

plot <- ggraph(bigram_graph, layout = "fr") +
        geom_edge_link() +
        geom_node_point(color = vcount(bigram_graph) , size = 5) +
        geom_node_text(aes(label = name), vjust = 1, hjust = 1) +
        theme_void()

girafe(ggobj = plot, width_svg = 10, height_svg = 10,
       options = list(opts_sizing(rescale = TRUE, width = .6)))

```


</div>